Embedded feature fusion for multi-view multi-label feature selection

With the explosive growth of data sources, multi-view multi-label learning (MVML) has garnered significant attention. However, the task of selecting informative features in MVML becomes more challenging as the dimensionality increase. Existing methods often extract information separately from the consensus part and the complementary part, potentially leading to noise attributed to ambiguous segmentation. In this paper, we propose an embedded feature selection model that combines with two aspects, which are the feature fusion between views and feature enhancement. Firstly, we calculate the adaptive weight of each view based on the local structure relations, and integrate it into one unified feature matrix. Subsequently, the mapping between unified feature matrix and ground-truth label matrix is established. Furthermore, a regularizer for the feature weight of each view is constructed to emphasize its characteristic, respectively. As a result, the relationship for inter-view and intra-view has been simultaneously considered, preserving comprehensive information of features by minimizing the difference between two types of feature weight. Experimental results demonstrate the superior performance of our method in coping with feature selection. • A learning process for emphasizing fusion process and distinctive matrix solving. • The global and local feature weights are combined to improve the performance. • The rationality of objective function is discussed and proved by experiments. • The optimization process is efficient with provable convergence.